Depends on what you mean by same geographical locations, but that can vary a lot. If you’re looking over 100’s of kilometers, there will be both poor and wealthy districts. If you’re looking within a single city, there will be poor and wealthy districts. This really only gets informative if you’re looking at different models used in the exact same polling place and even then it could be no more than correlation for other reasons (maybe for example poorer people prefer the older machines because they’re more familiar while wealthier people prefer newer machines because it matches their iPhone).
If voting preference is at all correlated to income, and what models of voting machines used at a polling place are correlated to the wealth of that district, then you will likely find a correlation between voting machine model and voter preference, with the older/cheaper model showing a preference for the candidate more favored by poorer people.
It’s not a sign there was fraud. Did you look at whether voting on newer models showed a higher preference for Bolsonaro than the national average?
What if Bolsonaro had won and someone claimed that the newer machines were built while he was in office so they were clearly programmed to favor him? Would you accept that narrative based purely on a correlation in data?
> maybe for example poorer people prefer the older machines because they’re more familiar while wealthier people prefer newer machines because it matches their iPhone
The machines look the same to the voter and we can't choose which machine to vote on. Each citizen is assigned an electoral zone and a section within that zone. One voting machine captures the votes of every section. In my neighborhood, for example, the voting took place at a school and every classroom had a different voting machine, one for each section.
It'd be extremely suspicious if it turned out that the people voting one room away from me showed statistically significant differences from the other sections.
> Did you look at whether voting on newer models showed a higher preference for Bolsonaro than the national average?
Looks like Bolsonaro wins if only 2020 models are evaluated.
> What if Bolsonaro had won and someone claimed that the newer machines were built while he was in office so they were clearly programmed to favor him? Would you accept that narrative based purely on a correlation in data?
Clearly we'd be having the same election denialism problems we're having now...
If voting preference is at all correlated to income, and what models of voting machines used at a polling place are correlated to the wealth of that district, then you will likely find a correlation between voting machine model and voter preference, with the older/cheaper model showing a preference for the candidate more favored by poorer people.
It’s not a sign there was fraud. Did you look at whether voting on newer models showed a higher preference for Bolsonaro than the national average?
What if Bolsonaro had won and someone claimed that the newer machines were built while he was in office so they were clearly programmed to favor him? Would you accept that narrative based purely on a correlation in data?